descriptinc/melgan-neurips
GAN-based Mel-Spectrogram Inversion Network for Text-to-Speech Synthesis
This project helps convert text-to-speech by taking a 'mel-spectrogram' – a visual representation of sound frequencies over time – and transforming it into clear, natural-sounding audio waveforms. This allows for the creation of synthetic speech from text inputs. It is designed for researchers and engineers working on speech synthesis and audio generation applications.
1,037 stars. No commits in the last 6 months.
Use this if you need to quickly and efficiently convert mel-spectrograms into high-quality, coherent raw audio waveforms for speech generation or music synthesis.
Not ideal if you are looking for a pre-built, end-user application for general text-to-speech without needing to interact with mel-spectrogram representations.
Stars
1,037
Forks
213
Language
Python
License
MIT
Category
Last pushed
Aug 28, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/descriptinc/melgan-neurips"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
yeyupiaoling/MASR
Pytorch实现的流式与非流式的自动语音识别框架，同时兼容在线和离线识别，目前支持Conformer、Squeezeformer、DeepSpeech2模型，支持多种数据增强方法。
shivammehta25/Matcha-TTS
[ICASSP 2024] 🍵 Matcha-TTS: A fast TTS architecture with conditional flow matching
coqui-ai/TTS
🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production
DigitalPhonetics/IMS-Toucan
Controllable and fast Text-to-Speech for over 7000 languages!
gabrielmittag/NISQA
NISQA - Non-Intrusive Speech Quality and TTS Naturalness Assessment